Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate being "in" a certain condition or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "in" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    in state or position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endregion
    -0.74
    RegressionTest
    -0.66
     pamamagitan
    -0.58
     cref
    -0.57
    Uninitialized
    -0.56
    期刊论文
    -0.55
     mangel
    -0.54
    ueves
    -0.54
     Itself
    -0.54
     ferrovia
    -0.53
    POSITIVE LOGITS
    SourceChecksum
    0.82
     position
    0.69
     mood
    0.67
     mode
    0.62
    TintMode
    0.62
     touch
    0.62
    Bronnen
    0.60
    expandindo
    0.60
     debt
    0.60
     control
    0.57
    Act Density 0.267%

    No Known Activations